SCOPE-HN

SCOPE-HN: A Segmentation-based Collection of Oropharyngeal Structures Using Flexible Endoscopy for Head and Neck Cancers Oropharyngeal cancer (OPC) is one of the few cancers with rising incidence, driven primarily by increasing rates of human papillomavirus (HPV)-associated disease. Early detection and accurate delineation of OPC are critical for diagnosis and treatment planning, but remain challenging due to anatomical complexity and variability in clinical expertise. The SCOPE-HN dataset addresses this clinical need by providing a comprehensive collection of expert-annotated endoscopic imaging data for machine learning research in oropharyngeal cancer detection and analysis. The dataset consists of 942 RGB images from 106 patients with histologically confirmed oropharyngeal cancer, collected at Stanford University between 2015-2023.SCOPE-HN：基于分割的头颈部癌柔性内镜口咽结构数据集 口咽癌（Oropharyngeal Cancer, OPC）是为数不多发病率呈上升趋势的癌种，其增长主要由人乳头瘤病毒（Human Papillomavirus, HPV）相关疾病的患病率升高所驱动。口咽癌的早期检出与精准解剖结构勾画，对临床诊断及治疗方案制定均具有关键价值，但受限于头颈部解剖结构的复杂性以及临床医师诊疗经验的个体差异，此类临床工作仍存在诸多挑战。 SCOPE-HN数据集正是为满足这一临床需求而构建，它提供了经过专家标注的内镜影像数据集，可用于口咽癌检测与分析相关的机器学习研究。该数据集包含2015年至2023年间在斯坦福大学收集的、来自106名经组织病理学确诊的口咽癌患者的942张RGB图像。

搜集汇总

背景与挑战

背景概述

SCOPE-HN是一个专注于口咽癌的内窥镜图像数据集，包含942张来自106名患者的RGB图像，并配有专家标注的像素级分割掩码，覆盖12个语义类别。该数据集旨在支持机器学习研究，用于口咽癌的检测、分析和解剖结构识别，同时提供详细的临床元数据以促进模型开发。